An Improved Approach to Software Defect Prediction using a Hybrid Machine Learning Model

Software defect prediction is an intricate but essential software testing related activity. As a solution to it, we have recently proposed HyGRAR, a hybrid classification model which combines Gradual Relational Association Rules (GRARs) with ANNs. ANNs were used to learn gradual relations that were then considered in a mining process so as to discover the interesting GRARs characterizing the defective and non-defective software entities, respectively. The classification of a new entity based on the discriminative GRARs was made through a non-adaptive heuristic method. In current paper, we propose to enhance HyGRAR through autonomously learning the classification methodology. Evaluation experiments performed on two open-source data sets indicate that the enhanced HyGRAR classifier outperforms the related approaches evaluated on the same two data sets.